MCP server
Trinity Research
dk.humanified/trinity-research
Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools
Fact-check claims against live web sources: verdict, consensus, cited sources, PII redaction.
Working at last checkVerified publisher: humanified.dkAbout 856 tokens per request once connected4 tools
https://trinity-v2-mcp.fly.dev/mcp
At a glance
- Type
- MCP server
- Publisher
- humanified.dk (verified by the MCP Registry)
- Status
- Working at last check
- Tools
- 4
- Token cost
- About 856 tokens per request
- Sets up in
- Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok
- Last checked
- 26 Oct 2026, 08:29 UTC
Connect it to your agent
Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.
Claude Code
claude mcp add --transport http trinity-research https://trinity-v2-mcp.fly.dev/mcp
Claude Desktop
Settings → Connectors → Add custom connector, and paste the URL.
Codex (config.toml)
[mcp_servers.trinity-research] url = "https://trinity-v2-mcp.fly.dev/mcp"
Gemini CLI
{"mcpServers":{"trinity-research":{"httpUrl":"https://trinity-v2-mcp.fly.dev/mcp"}}}
Cursor
{"mcpServers":{"trinity-research":{"url":"https://trinity-v2-mcp.fly.dev/mcp"}}}
VS Code
{"servers":{"trinity-research":{"type":"http","url":"https://trinity-v2-mcp.fly.dev/mcp"}}}
Antigravity
agy mcp add trinity-research https://trinity-v2-mcp.fly.dev/mcp
ChatGPT
Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.
OpenAI API (Responses tools)
{"type":"mcp","server_label":"trinity-research","server_url":"https://trinity-v2-mcp.fly.dev/mcp","require_approval":"always"}
Grok (xAI API tools)
{"type":"mcp","server_label":"trinity-research","server_url":"https://trinity-v2-mcp.fly.dev/mcp"}
Tools
multi_source_validator~260 tokens
Verify a factual claim against multiple live web sources (Brave). Returns a JSON object with a verdict (supported / contradicted / unverified), a 0-1 consensus score, short reasoning, and the actual cited sources (ref, title, url). Judges only from retrieved sources — never fabricates. 'contradictedping~117 tokens
Liveness probe. Returns 'pong' plus any supplied message.privacy_shield_redact~164 tokens
Redact personally identifiable information (PII) from text — emails, phone numbers, IDs, names, etc. Returns the masked text plus a count of what was redacted by type. Privacy-by-default for research workflows.structured_brief_synthesizer~315 tokens
Synthesize multiple sources into a structured, cited brief. format: 'synthesis' (narrative), 'summary' (bullets), or 'integrated' (how sources connect). Cites inline as [n]; never invents facts beyond the sources.
Browse
Related MCP servers
- Bob Research Tools
Paid web research, news, prediction-market evidence, company briefs and fact-checks (x402 USDC) - HubVibe: Pay-per-Call Agent Tools: Web Search, Email Verify, KYC Screening, Stocks, Crypto, News
70+ pay-per-call tools for AI agents: web search, email verify, KYC, stocks, crypto, news, data - Fidenta Verify
Independent fact-checking for AI answers: a verdict and sources for every claim. - 402oracle
Signed verification attestations for agent decisions: business, price, freshness, claim checks. - CutGPT Research & Fact-Check
Free fact-checks, papers, source vetting, plus verified AI pricing, comparisons, guides, and tools. - AgentIndex x402
Jev-powered decisions, web search, PDF/web to Markdown, summarize. From $0.001, no API key. - Agent Data Tools
333 agent tools: chain data, prices, sanctions, web, PDF. 25 free calls, then from $0.002. - Storskarvia
Writing studio for novels and screenplays: read your projects and run cited fact-checks.
Badge for your README
[](https://aptlynx.net/servers/dk.humanified/trinity-research)
Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents